Search Results for author:
Found 4 papers, 0 papers with code
BEA: Revisiting anchor-based object detection DNN using Budding Ensemble Architecture
The proposed loss functions in BEA improve the confidence score calibration and lower the uncertainty error, which results in a better distinction of true and false positives and, eventually, higher accuracy of the object detection models.
Exploring Resiliency to Natural Image Corruptions in Deep Learning using Design Diversity
We compare ensembles created with diverse model architectures trained either independently or through a Neural Architecture Search technique and evaluate the correlation of prediction-based and attribution-based diversity to the final ensemble accuracy.
Evaluation of Confidence-based Ensembling in Deep Learning Image Classification
The key idea is to create successive model experts for samples that were difficult (not necessarily incorrectly classified) by the preceding model.
Multi-Objective Design Space Exploration for the Optimization of the HEVC Mode Decision Process
Finding the best possible encoding decisions for compressing a video sequence is a highly complex problem.
